Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to highly energetic physical processes or equipment, such as pulses, plasma, energy, and blasts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.76
    sm
    -0.76
    orned
    -0.75
     Riyadh
    -0.73
     Sask
    -0.72
     Rockefeller
    -0.72
    neau
    -0.71
    quickShipAvailable
    -0.71
    andals
    -0.69
    ahime
    -0.69
    POSITIVE LOGITS
     pulse
    1.05
    audio
    0.98
     pulses
    0.98
    ulse
    0.91
     Width
    0.91
     puls
    0.88
    beam
    0.86
     heartbeat
    0.82
    Audio
    0.82
     ox
    0.81
    Act Density 6.565%

    No Known Activations